TP-Agent: An Auditable LLM Agent for Predicting Pollutant Transformation Products in Oxidative Water Treatment

Abstract Predicting the transformation products (TPs) of organic micropollutants is important for characterizing their chemical fate during oxidative water treatment and prioritizing candidate structures for high-resolution mass spectrometry (HRMS) analysis. Limited labeled data and diverse reaction pathways make this task challenging. TP-Agent combines a large language model (LLM), training-only analog retrieval, and executable atom/bond edits to rank TP candidates with inspectable structural records. On 231 standardized-parent-disjoint reactions, TP-Agent achieved 78.8% strict Top-5 accuracy, compared with 65.8% for the bare LLM, 76.2% for standalone retrieval-augmented generation (RAG), and 56.3 ± 1.5% for TP-Transformer across three training seeds. Parent-clustered bootstrap analysis supported the gain over the bare LLM; the 2.6-percentage-point difference from RAG was not statistically significant. Retrieval supplied most of the accuracy gain, while graph execution added candidate-linked structural records. Among 1095 candidates, 92.7% had exact edit-replay or deterministic-projection records, measuring structural linkage rather than mechanistic validity. Where available, candidate-linked LLM rationales provide chemical hypotheses for inspection. Estimated parallel latency and API-equivalent cost were 3.5 and 7.4 times those of RAG, respectively. TP-Agent thus combines TP candidate ranking with traceable structural operations and inspectable chemical hypotheses for HRMS follow-up.

Authors

Institutions

Publication Details

Journal
Environmental Science & Technology
Published
2026-11-12
DOI
https://doi.org/10.1021/acs.est.6c09725
Primary Topic
Advanced oxidation water treatment
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

TP-Agent: An Auditable LLM Agent for Predicting Pollutant Transformation Products in Oxidative Water Treatment

Shifa Zhong
Environmental Science & Technology
Advanced oxidation water treatment
article

TP-Agent: An Auditable LLM Agent for Predicting Pollutant Transformation Products in Oxidative Water Treatment

Shifa Zhong
article en

Abstract

Abstract Predicting the transformation products (TPs) of organic micropollutants is important for characterizing their chemical fate during oxidative water treatment and prioritizing candidate structures for high-resolution mass spectrometry (HRMS) analysis. Limited labeled data and diverse reaction pathways make this task challenging. TP-Agent combines a large language model (LLM), training-only analog retrieval, and executable atom/bond edits to rank TP candidates with inspectable structural records. On 231 standardized-parent-disjoint reactions, TP-Agent achieved 78.8% strict Top-5 accuracy, compared with 65.8% for the bare LLM, 76.2% for standalone retrieval-augmented generation (RAG), and 56.3 ± 1.5% for TP-Transformer across three training seeds. Parent-clustered bootstrap analysis supported the gain over the bare LLM; the 2.6-percentage-point difference from RAG was not statistically significant. Retrieval supplied most of the accuracy gain, while graph execution added candidate-linked structural records. Among 1095 candidates, 92.7% had exact edit-replay or deterministic-projection records, measuring structural linkage rather than mechanistic validity. Where available, candidate-linked LLM rationales provide chemical hypotheses for inspection. Estimated parallel latency and API-equivalent cost were 3.5 and 7.4 times those of RAG, respectively. TP-Agent thus combines TP candidate ranking with traceable structural operations and inspectable chemical hypotheses for HRMS follow-up.

Environmental Science & Technology
Tongji University (CN)
National Natural Science Foundation of China, Ministry of Education of the People's Republic of China
Clean water and sanitation
Advanced oxidation water treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon